molecule_counter.py 文件源码

def concatenate_sort(out_filename, in_filenames, sort_cols, metrics=None):
        in_mcs = [MoleculeCounter.open(f, 'r') for f in in_filenames]
        out_mc = MoleculeCounter.open(out_filename, mode='w')
        if metrics is None:
            metrics = in_mcs[0].get_all_metrics()
        out_mc.set_all_metrics(metrics)
        for col, array in in_mcs[0].ref_columns.iteritems():
            out_mc.set_ref_column(col, array[:])
        sort_array = []
        # reverse sort columns so they get sorted in the right order
        for col in reversed(sort_cols):
            sort_array.append(np.concatenate([mc.get_column(col) for mc in in_mcs]))
        sort_index = np.lexsort(sort_array)
        for col in MOLECULE_INFO_COLUMNS:
            col_sorted = np.concatenate([mc.get_column(col) for mc in in_mcs])[sort_index]
            out_mc.add_many(col, col_sorted)
        for mc in in_mcs:
            mc.close()
        out_mc.save()